Skip to content

BUG: Mismatch between get and set behavior for slices of floating indices (fixes #2727) #2777

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

BUG: Mismatch between get and set behavior for slices of floating indices (fixes #2727) #2777

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 25 additions & 19 deletions pandas/core/indexing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -435,23 +435,27 @@ def _convert_to_indexer(self, obj, axis=0):
if isinstance(obj, slice):
ltype = labels.inferred_type

if ltype == 'floating':
int_slice = _is_int_slice(obj)
else:
# floats that are within tolerance of int used
int_slice = _is_index_slice(obj)
# in case of providing all floats, use label-based indexing
float_slice = (labels.inferred_type == 'floating'
and _is_float_slice(obj))

# floats that are within tolerance of int used as positions
int_slice = _is_index_slice(obj)

null_slice = obj.start is None and obj.stop is None
# could have integers in the first level of the MultiIndex

# could have integers in the first level of the MultiIndex,
# in which case we wouldn't want to do position-based slicing
position_slice = (int_slice
and not ltype == 'integer'
and not isinstance(labels, MultiIndex))
and not isinstance(labels, MultiIndex)
and not float_slice)

start, stop = obj.start, obj.stop

# last ditch effort: if we are mixed and have integers
try:
if 'mixed' in ltype and int_slice:
if position_slice and 'mixed' in ltype:
if start is not None:
i = labels.get_loc(start)
if stop is not None:
Expand All @@ -468,7 +472,7 @@ def _convert_to_indexer(self, obj, axis=0):
indexer = labels.slice_indexer(start, stop, obj.step)
except Exception:
if _is_index_slice(obj):
if labels.inferred_type == 'integer':
if ltype == 'integer':
raise
indexer = obj
else:
Expand Down Expand Up @@ -539,34 +543,36 @@ def _get_slice_axis(self, slice_obj, axis=0):

labels = obj._get_axis(axis)

int_slice = _is_index_slice(slice_obj)

start = slice_obj.start
stop = slice_obj.stop
ltype = labels.inferred_type

# in case of providing all floats, use label-based indexing
float_slice = (labels.inferred_type == 'floating'
and _is_float_slice(slice_obj))

# floats that are within tolerance of int used as positions
int_slice = _is_index_slice(slice_obj)

null_slice = slice_obj.start is None and slice_obj.stop is None

# could have integers in the first level of the MultiIndex, in which
# case we wouldn't want to do position-based slicing
# could have integers in the first level of the MultiIndex,
# in which case we wouldn't want to do position-based slicing
position_slice = (int_slice
and labels.inferred_type != 'integer'
and not ltype == 'integer'
and not isinstance(labels, MultiIndex)
and not float_slice)

start, stop = slice_obj.start, slice_obj.stop

# last ditch effort: if we are mixed and have integers
try:
if 'mixed' in labels.inferred_type and int_slice:
if position_slice and 'mixed' in ltype:
if start is not None:
i = labels.get_loc(start)
if stop is not None:
j = labels.get_loc(stop)
position_slice = False
except KeyError:
if labels.inferred_type == 'mixed-integer-float':
if ltype == 'mixed-integer-float':
raise

if null_slice or position_slice:
Expand All @@ -576,7 +582,7 @@ def _get_slice_axis(self, slice_obj, axis=0):
indexer = labels.slice_indexer(start, stop, slice_obj.step)
except Exception:
if _is_index_slice(slice_obj):
if labels.inferred_type == 'integer':
if ltype == 'integer':
raise
indexer = slice_obj
else:
Expand Down
39 changes: 39 additions & 0 deletions pandas/tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1183,6 +1183,45 @@ def test_getitem_setitem_float_labels(self):
self.assertRaises(Exception, df.ix.__getitem__, slice(1, 2))
self.assertRaises(Exception, df.ix.__setitem__, slice(1, 2), 0)

# #2727
index = Index([1.0, 2.5, 3.5, 4.5, 5.0])
df = DataFrame(np.random.randn(5, 5), index=index)

# positional slicing!
result = df.ix[1.0:5]
expected = df.reindex([2.5, 3.5, 4.5, 5.0])
assert_frame_equal(result, expected)
self.assertEqual(len(result), 4)

# positional again
result = df.ix[4:5]
expected = df.reindex([5.0])
assert_frame_equal(result, expected)
self.assertEqual(len(result), 1)

# label-based
result = df.ix[1.0:5.0]
expected = df.reindex([1.0, 2.5, 3.5, 4.5, 5.0])
assert_frame_equal(result, expected)
self.assertEqual(len(result), 5)

cp = df.copy()
# positional slicing!
cp.ix[1.0:5] = 0
self.assert_((cp.ix[1.0:5] == 0).values.all())
self.assert_((cp.ix[0:1] == df.ix[0:1]).values.all())

cp = df.copy()
# positional again
cp.ix[4:5] = 0
self.assert_((cp.ix[4:5] == 0).values.all())
self.assert_((cp.ix[0:4] == df.ix[0:4]).values.all())

cp = df.copy()
# label-based
cp.ix[1.0:5.0] = 0
self.assert_((cp.ix[1.0:5.0] == 0).values.all())

def test_setitem_single_column_mixed(self):
df = DataFrame(randn(5, 3), index=['a', 'b', 'c', 'd', 'e'],
columns=['foo', 'bar', 'baz'])
Expand Down